#!/usr/bin/env bash
# Candidates end-to-end — first deep-field reality test.
#
# Spins up storaged + embedd + vectord + matrixd + gateway, ingests
# the 1000-candidate corpus from
# /home/profit/lakehouse/data/datasets/candidates.parquet via the
# corpusingest substrate, then runs a real staffing query through
# /v1/matrix/search and prints the top 5 hits.
#
# Requires: Ollama on :11434 with nomic-embed-text loaded. If absent,
# this script exits 0 with a "skipped" message — same contract as
# g2_smoke.
#
# Usage: ./scripts/candidates_e2e.sh
#        ./scripts/candidates_e2e.sh "your custom query here"

set -euo pipefail
cd "$(dirname "$0")/.."

export PATH="$PATH:/usr/local/go/bin"

QUERY="${1:-Python AWS Docker engineer in Chicago available now}"

if ! curl -sS --max-time 3 http://localhost:11434/api/tags >/dev/null 2>&1; then
  echo "[candidates-e2e] Ollama not reachable on :11434 — skipping (matches g2_smoke contract)"
  exit 0
fi

echo "[candidates-e2e] building binaries..."
go build -o bin/ ./cmd/storaged ./cmd/embedd ./cmd/vectord ./cmd/matrixd ./cmd/gateway ./scripts/staffing_candidates

pkill -f "bin/(storaged|embedd|vectord|matrixd|gateway)" 2>/dev/null || true
sleep 0.3

PIDS=()
TMP="$(mktemp -d)"
CFG="$TMP/e2e.toml"
cleanup() {
  echo "[candidates-e2e] cleanup"
  for p in "${PIDS[@]}"; do [ -n "$p" ] && kill "$p" 2>/dev/null || true; done
  rm -rf "$TMP"
}
trap cleanup EXIT INT TERM

# Custom toml: vectord persistence disabled so the candidates index
# doesn't survive the run. Without this, re-running pollutes the
# shared MinIO `_vectors/` prefix and breaks g1p_smoke's "this is
# the only persisted index" assertion (caught 2026-04-29).
cat > "$CFG" <<EOF
[gateway]
bind = "127.0.0.1:3110"
storaged_url = "http://127.0.0.1:3211"
catalogd_url = "http://127.0.0.1:3212"
ingestd_url  = "http://127.0.0.1:3213"
queryd_url   = "http://127.0.0.1:3214"
vectord_url  = "http://127.0.0.1:3215"
embedd_url   = "http://127.0.0.1:3216"
pathwayd_url = "http://127.0.0.1:3217"
matrixd_url  = "http://127.0.0.1:3218"

[vectord]
bind = "127.0.0.1:3215"
storaged_url = ""

[matrixd]
bind = "127.0.0.1:3218"
embedd_url  = "http://127.0.0.1:3216"
vectord_url = "http://127.0.0.1:3215"
EOF

poll_health() {
  local port="$1" deadline=$(($(date +%s) + 5))
  while [ "$(date +%s)" -lt "$deadline" ]; do
    if curl -sS --max-time 1 "http://127.0.0.1:$port/health" >/dev/null 2>&1; then return 0; fi
    sleep 0.05
  done
  return 1
}

echo "[candidates-e2e] launching stack..."
./bin/storaged -config "$CFG" > /tmp/storaged.log 2>&1 & PIDS+=($!)
poll_health 3211 || { echo "storaged failed"; tail /tmp/storaged.log; exit 1; }

./bin/embedd -config "$CFG" > /tmp/embedd.log 2>&1 & PIDS+=($!)
poll_health 3216 || { echo "embedd failed"; tail /tmp/embedd.log; exit 1; }

./bin/vectord -config "$CFG" > /tmp/vectord.log 2>&1 & PIDS+=($!)
poll_health 3215 || { echo "vectord failed"; tail /tmp/vectord.log; exit 1; }

./bin/matrixd -config "$CFG" > /tmp/matrixd.log 2>&1 & PIDS+=($!)
poll_health 3218 || { echo "matrixd failed"; tail /tmp/matrixd.log; exit 1; }

./bin/gateway -config "$CFG" > /tmp/gateway.log 2>&1 & PIDS+=($!)
poll_health 3110 || { echo "gateway failed"; tail /tmp/gateway.log; exit 1; }

echo "[candidates-e2e] stack up; running ingest + reality test query..."
echo
./bin/staffing_candidates -query "$QUERY"